Structure Causal Models and LLMs Integration in Medical Visual Question Answering

Zibo Xu;Qiang Li;Weizhi Nie;Weijie Wang;Anan Liu
{"title":"Structure Causal Models and LLMs Integration in Medical Visual Question Answering","authors":"Zibo Xu;Qiang Li;Weizhi Nie;Weijie Wang;Anan Liu","doi":"10.1109/TMI.2025.3564320","DOIUrl":null,"url":null,"abstract":"Medical Visual Question Answering (MedVQA) aims to answer medical questions according to medical images. However, the complexity of medical data leads to confounders that are difficult to observe, so bias between images and questions is inevitable. Such cross-modal bias makes it challenging to infer medically meaningful answers. In this work, we propose a causal inference framework for the MedVQA task, which effectively eliminates the relative confounding effect between the image and the question to ensure the precision of the question-answering (QA) session. We are the first to introduce a novel causal graph structure that represents the interaction between visual and textual elements, explicitly capturing how different questions influence visual features. During optimization, we apply the mutual information to discover spurious correlations and propose a multi-variable resampling front-door adjustment method to eliminate the relative confounding effect, which aims to align features based on their true causal relevance to the question-answering task. In addition, we also introduce a prompt strategy that combines multiple prompt forms to improve the model’s ability to understand complex medical data and answer accurately. Extensive experiments on three MedVQA datasets demonstrate that 1) our method significantly improves the accuracy of MedVQA, and 2) our method achieves true causal correlations in the face of complex medical data.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"44 8","pages":"3476-3489"},"PeriodicalIF":0.0000,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on medical imaging","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10979774/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Medical Visual Question Answering (MedVQA) aims to answer medical questions according to medical images. However, the complexity of medical data leads to confounders that are difficult to observe, so bias between images and questions is inevitable. Such cross-modal bias makes it challenging to infer medically meaningful answers. In this work, we propose a causal inference framework for the MedVQA task, which effectively eliminates the relative confounding effect between the image and the question to ensure the precision of the question-answering (QA) session. We are the first to introduce a novel causal graph structure that represents the interaction between visual and textual elements, explicitly capturing how different questions influence visual features. During optimization, we apply the mutual information to discover spurious correlations and propose a multi-variable resampling front-door adjustment method to eliminate the relative confounding effect, which aims to align features based on their true causal relevance to the question-answering task. In addition, we also introduce a prompt strategy that combines multiple prompt forms to improve the model’s ability to understand complex medical data and answer accurately. Extensive experiments on three MedVQA datasets demonstrate that 1) our method significantly improves the accuracy of MedVQA, and 2) our method achieves true causal correlations in the face of complex medical data.
结构因果模型与llm在医学视觉问答中的整合
医学视觉问答(MedVQA)旨在根据医学图像回答医学问题。然而,医疗数据的复杂性导致了难以观察到的混杂因素,因此图像和问题之间的偏差是不可避免的。这种跨模式的偏见使得我们很难推断出医学上有意义的答案。在这项工作中,我们提出了一个MedVQA任务的因果推理框架,该框架有效地消除了图像和问题之间的相对混淆效应,以确保问答(QA)会话的精度。我们首先引入了一种新的因果图结构,它代表了视觉和文本元素之间的相互作用,明确地捕捉了不同的问题如何影响视觉特征。在优化过程中,我们利用互信息来发现虚假相关性,并提出了一种多变量重采样前门调整方法来消除相对混淆效应,该方法旨在根据特征与问答任务的真实因果相关性来对齐特征。此外,我们还引入了多种提示形式组合的提示策略,以提高模型对复杂医疗数据的理解能力和准确回答能力。在三个MedVQA数据集上的大量实验表明:1)我们的方法显著提高了MedVQA的准确性;2)面对复杂的医疗数据,我们的方法实现了真正的因果关联。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信